sys.path.append('./resources/libraries') import os import tensorflow as tf from tensorflow.keras.optimizers import Adam from tensorflow.keras.applications import MobileNetV2 from tensorflow.keras.layers import BatchNormalization, Conv2D from tensorflow.keras.models import Model from ei_tensorflow.constrained_object_detection import models, dataset, metrics def build_model(input_shape: tuple, weights: str, alpha: float, num_classes: int) -> tf.keras.Model: """ Construct a constrained object detection model. Args: input_shape: Passed to MobileNet construction. weights: Weights for initialization of MobileNet where None implies random initialization. alpha: MobileNet alpha value. num_classes: Number of classes, i.e. final dimension size, in output. Returns: Uncompiled keras model. Model takes (B, H, W, C) input and returns (B, H//8, W//8, num_classes) logits. """ #! First create full mobile_net_V2 from (HW, HW, C) input #! to (HW/8, HW/8, C) output mobile_net_v2 = MobileNetV2(input_shape=input_shape, weights=weights, alpha=alpha, include_top=True) #! Default batch norm is configured for huge networks, let's speed it up for layer in mobile_net_v2.layers: if type(layer) == BatchNormalization: layer.momentum = 0.9 base_network_output = mobile_net_v2.get_layer( 'block_6_expand_relu').output #! (HW/8, HW/8, C) head_of_mobile_net = Model(inputs=mobile_net_v2.input, outputs=base_network_output, name='mobile_net_to_eighth_eighth') #! Now attach a small additional head on the MobileNet model = Conv2D(filters=32, kernel_size=1, strides=1, activation='relu', name='head')(head_of_mobile_net.output) logits = Conv2D(filters=num_classes, kernel_size=1, strides=1, activation=None, name='logits')(model) return Model(inputs=head_of_mobile_net.input, outputs=logits) def train(num_classes: int, learning_rate: float, num_epochs: int, alpha: float, object_weight: int, train_dataset: tf.data.Dataset, validation_dataset: tf.data.Dataset, input_shape: tuple) -> tf.keras.Model: """ Construct and train a constrained object detection model. Args: num_classes: Number of classes in datasets. This does not include implied background class introduced by segmentation map dataset conversion. learning_rate: Learning rate for Adam. num_epochs: Number of epochs passed to model.fit alpha: Alpha used to construct MobileNet. Pretrained weights will be used if there is a matching set. object_weight: The weighting to give the object in the loss function where background has an implied weight of 1.0. train_dataset: Training dataset of (x, (bbox, one_hot_y)) validation_dataset: Validation dataset of (x, (bbox, one_hot_y)) input_shape: The shape of the model's input Returns: Trained keras model. Constructs a new constrained object detection model with num_classes+1 outputs (denoting the classes with an implied background class of 0). Both training and validation datasets are adapted from (x, (bbox, one_hot_y)) to (x, segmentation_map). Model is trained with a custom weighted cross entropy function. """ num_classes_with_background = num_classes + 1 input_width_height = None width, height, _channels = input_shape if width != height: raise Exception(f"Only square inputs are supported; not {input_shape}") input_width_height = width #! Use pretrained weights, if we have them for configured alpha. if alpha == 0.1: weights = "./transfer-learning-weights/edgeimpulse/MobileNetV2.0_1.96x96.grayscale.bsize_64.lr_0_05.epoch_441.val_loss_4.13.val_accuracy_0.2.hdf5" elif alpha == 0.35: weights = "./transfer-learning-weights/edgeimpulse/MobileNetV2.0_35.96x96.grayscale.bsize_64.lr_0_005.epoch_260.val_loss_3.10.val_accuracy_0.35.hdf5" else: weights = None if (weights is not None) and (not os.path.exists(weights)): print(f"WARNING: Pretrained weights {weights} unavailable; defaulting to random init") weights = None model = build_model( input_shape=(input_width_height, input_width_height, 1), weights=weights, alpha=alpha, num_classes=num_classes_with_background ) #! Derive output size from model model_output_shape = model.layers[-1].output.shape _batch, width, height, num_classes = model_output_shape if width != height: raise Exception(f"Only square outputs are supported; not {model_output_shape}") output_width_height = width #! Build weighted cross entropy loss specific to this model size weighted_xent = models.construct_weighted_xent_fn(model.output.shape, object_weight) print(model.summary()) model.compile(loss=weighted_xent, optimizer=Adam(learning_rate=learning_rate)) #! Wrap bbox datasets with adapters for segmentation maps train_segmentation_dataset = dataset.bbox_to_segmentation( train_dataset, input_width_height, output_width_height, num_classes_with_background) validation_segmentation_dataset = dataset.bbox_to_segmentation( validation_dataset, input_width_height, output_width_height, num_classes_with_background) #! Create callback that will do centroid scoring on end of epoch against #! validation data. callbacks = [metrics.CentroidScoring( validation_dataset, output_width_height, num_classes_with_background )] model.fit(train_segmentation_dataset, validation_data=validation_segmentation_dataset, epochs=num_epochs, callbacks=callbacks, verbose=0) return model model = train(num_classes=classes, learning_rate=0.001, num_epochs=100, alpha=0.35, object_weight=100, train_dataset=train_dataset, validation_dataset=validation_dataset, input_shape=MODEL_INPUT_SHAPE) override_mode = 'segmentation' disable_per_channel_quantization = False